© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3817
    Prev
    Next
    INDEX
    Explanations

    clinical study parameters and significant relationships in research data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    statistical terms and mathematical symbols related to scientific analysis, such as regression coefficients, correlations, p-values, and statistical notation.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __':
    -0.73
    __":
    -0.68
     ब्रेकडाउन
    -0.60
    __':
    -0.59
    ſelf
    -0.58
    ]")]
    -0.57
    __":
    -0.55
     Reſ
    -0.53
    ſelves
    -0.52
     Eſ
    -0.49
    POSITIVE LOGITS
    MessageTagHelper
    0.46
    welijk
    0.42
    Unmarshal
    0.41
     ferramenta
    0.41
    ustimmung
    0.41
     scores
    0.40
     drog
    0.39
    validates
    0.39
     становника
    0.39
    ➟
    0.38
    Activations Density 0.660%

    No Known Activations